SWDEV-301667 - Create TS for each node recorded in graph
- Create a vector to allow multiple TS to be stored in Command. - This would mean we dont wait for entire batch in Accumulate command to finish when we exhaust signals. - Reduce the number of signals created at init to 64. This min value may still need to be tuned but the KFD allows max of 4094 interrupt signals per device. - Store kernel names whenever they are available and not just when profiling. If we dynamically enable profiling like for Torch, a crash can happen if hipGraphInstantiate wasnt included in Torch profile scope beacuse we previously entered kernel names only when profiler is attached. Change-Id: I34e7881a25bbc763f82fdeb3408a8ea58e1ec006
Dieser Commit ist enthalten in:
@@ -51,7 +51,8 @@
|
||||
bool amd::ClGlEvent::waitForFence() {
|
||||
GLenum ret;
|
||||
// get fence id associated with fence event
|
||||
GLsync gs = reinterpret_cast<GLsync>(command().data());
|
||||
GLsync gs = !command().data().empty() ? reinterpret_cast<GLsync>(command().data().back())
|
||||
: nullptr;
|
||||
if (!gs) return false;
|
||||
|
||||
// Try to use DC and GLRC of current thread, if it doesn't exist
|
||||
|
||||
In neuem Issue referenzieren
Einen Benutzer sperren